what kind of NLP technique or model is used in rasa to build intent classification and entity recognition? and what is the use of tensorflow in rasa?
That is DIET model.
thanks @ChikkaUdayaSai…what about tensorflow…why rasa need tensorflow?
In the DIET architecture, they are using some deep learning architectures (Neural Networks). For that purpose, they are using Tensorflow.
Okay @ChikkaUdayaSai…from your explainintion I understand that diet is a rasa open source inbuilt nlp model for intent classification and entity recognition if am correct…and the algorithms which are tokenizers and featurizers are machine learning algorithms in order to tokenize and feuterize the input text from a user…did I get you??
@ChikkaUdayaSai…thank you so much…how is the flow works?..after entering an input…first the text will be tokenizers into words then what happens…am kind of stacked there until the bots response …what kind of flow does the text pass and the bot gives a response
It all depends on how you define those pipelines in your config file. First come first serve.
I will appreciate that.
@ChikkaUdayaSai…this is what my config file looks like
- name: "DucklingEntityExtractor" url: "http://localhost:8000" dimensions: ["time", "email"] # timezone: "Ethiopia/addis abeba" timeout: 3 - name: WhitespaceTokenizer - name: RegexFeaturizer - name: RegexEntityExtractor - name: LexicalSyntacticFeaturizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer analyzer: "char_wb" min_ngram: 1 max_ngram: 4 #- name: CRFEntityExtractor - name: DIETClassifier epochs: 100 - name: EntitySynonymMapper - name: ResponseSelector epochs: 100 #retrieval_intent: faq - name: FallbackClassifier threshold: 0.7 ``` ```policies: - name: MemoizationPolicy - name: TEDPolicy max_history: 8 epochs: 200 #- name: "coco_rasa.CoCoContextPolicy" - name: RulePolicy```